Tensor Density Estimator by Convolution-Deconvolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Yifan, Yang, Siyao, Khoo, Yuehaw, Wang, Daren
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915580487925760
author Peng, Yifan
Yang, Siyao
Khoo, Yuehaw
Wang, Daren
author_facet Peng, Yifan
Yang, Siyao
Khoo, Yuehaw
Wang, Daren
contents We propose a linear algebraic framework for performing density estimation. It consists of three simple steps: convolving the empirical distribution with certain smoothing kernels to remove the exponentially large variance; compressing the empirical distribution after convolution as a tensor train, with efficient tensor decomposition algorithms; and finally, applying a deconvolution step to recover the estimated density from such tensor-train representation. Numerical results demonstrate the high accuracy and efficiency of the proposed methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tensor Density Estimator by Convolution-Deconvolution
Peng, Yifan
Yang, Siyao
Khoo, Yuehaw
Wang, Daren
Numerical Analysis
15A69, 62Gxx
We propose a linear algebraic framework for performing density estimation. It consists of three simple steps: convolving the empirical distribution with certain smoothing kernels to remove the exponentially large variance; compressing the empirical distribution after convolution as a tensor train, with efficient tensor decomposition algorithms; and finally, applying a deconvolution step to recover the estimated density from such tensor-train representation. Numerical results demonstrate the high accuracy and efficiency of the proposed methods.
title Tensor Density Estimator by Convolution-Deconvolution
topic Numerical Analysis
15A69, 62Gxx
url https://arxiv.org/abs/2412.18964